Mirco Fuchs

Dr. Mirco Fuchs

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 September 2021 in Sensors
Verified
Journal Article
Open access
PDF file
FSFabian Schrumpf
Fabian Schrumpf
PFPatrick Frenzel
Patrick Frenzel
CAChristoph Aust
Christoph Aust
Georg OsterhoffGeorg Osterhoff
Georg Osterhoff
MFMirco Fuchs
Mirco Fuchs
Exploiting photoplethysmography signals (PPG) for non-invasive blood pressure (BP) measurement is interesting for various reasons. First, PPG can easily be measured using fingerclip sensors. Second, camera based approaches allow to derive remote PPG (rPPG) signals similar to PPG and therefore provide the opportunity for non-invasive measurements of BP. Various methods relying on machine learning techniques have recently been published. Performances are often reported as the mean average error (MAE) on the data which is problematic. This work aims to analyze the PPG- and rPPG based BP prediction error with respect to the underlying data distribution. First, we train established neural network (NN) architectures and derive an appropriate parameterization of input segments drawn from continuous PPG signals. Second, we use this parameterization to train NNs with a larger PPG dataset and carry out a systematic evaluation of the predicted blood pressure. The analysis revealed a strong systematic increase of the prediction error towards less frequent BP values across NN architectures. Moreover, we tested different train/test set split configurations which underpin the importance of a careful subject-aware dataset assignment to prevent overly optimistic results. Third, we use transfer learning to train the NNs for rPPG based BP prediction. The resulting performances are similar to the PPG-only case. Finally, we apply different personalization techniques and retrain our NNs with subject-specific data for both the PPG-only and rPPG case. Whilst the particular technique is less important, personalization reduces the prediction errors significantly.

1 November 2021 in Ecological Informatics
Verified
Journal Article
Closed access
FAFranz Anders
Franz Anders
AKAmmie K. Kalan
Ammie K. Kalan
HKHjalmar S. Kühl
Hjalmar S. Kühl
MFMirco Fuchs
Mirco Fuchs

1 September 2016 in Current Directions in Biomedical Engineering
Verified
Journal Article
Open access
PDF file
FSFabian Schrumpf
Fabian Schrumpf
MSMatthias Sturm
Matthias Sturm
GBGerold Bausch
Gerold Bausch
MFMirco Fuchs
Mirco Fuchs
The estimation of respiratory rates from contineous respiratory signals is commonly done using either fourier transformation or the zero-crossing method. This paper introduces another method which is based on the autocorrelation function of the respiratory signal. The respiratory signals can be measured either directly using a flow sensor or chest strap or indirectly on the basis of the electrocardiogram (ECG). We compare our method against other established methods on the basis of real-world ECG signals and use a respiration-based breathing frequency as a reference. Our method achieved the best agreement between respiration rates derived from directly and indirectly measured respiratory signals.

11 November 2020 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Open access
FAFranz Anders
Franz Anders
MHMario Hlawitschka
Mario Hlawitschka
MFMirco Fuchs
Mirco Fuchs
In this study we compared various neural network types for the task of automatic infant vocalization classification, i.e convolutional, recurrent and fully-connected networks as well as combinations of thereof. The goal was to first determine the optimal configuration for each network type to then identify the type with the highest overall performance. This investigation helps to employ neural networks more effectively to infant vocalization classification tasks, which typically offer low amounts of training data. To this end, we defined a unified neural network architecture scheme for audio classification from which we derived various network types. For each type we performed a semi-random hyperparameter search which employed regression trees to both focus the search space as well as derive insights on the most influential parameters. We finally compared the test performances of the best performing configurations in an contest-like setup. Our key findings are: (1) Networks with convolutional stages reached the highest performance, regardless of being combined with fully-connected or recurrent layers. (2) The most influential architectural hyperparameter for all types were the integration operations for reducing tensor dimensionality between network stages. The best performing configurations reached test performances of 75% unweighted average recall, surpassing previously published benchmarks.

8 February 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
VLValentin Lang
Valentin Lang
CHChristian Thomas Ernst Herrmann
Christian Thomas Ernst Herrmann
MFMirco Fuchs
Mirco Fuchs
SISteffen Ihlenfeldt
Steffen Ihlenfeldt
Additive manufacturing is gaining importance in a number of application areas, and there is an increased demand for mechanically resilient components. A way to improve the mechanical properties of parts made of thermoplastics is by using reinforcing material. The study demonstrates the development of a monitoring procedure for a fused filament fabrication-based co-extrusion process for manufacturing wire-reinforced thermoplastic components. Test components in two variants are produced, and data acquisition is carried out with a laser line scanner. The collected data are employed to train deep neural networks to classify the printed layers, aiming for the deep neural networks to be able to classify four different classes and identify layers with insufficient quality. A dedicated convolutional neural network is designed taking into account various factors such as layer architecture, data pre-processing and optimization methods. Several network architectures, including transfer learning (based on VGG16 and ResNet50), with and without fine-tuning, are compared in terms of their performance based on the F1 score. Both the transfer learning model with ResNet50 and the fine-tuning model achieve an F1 score of 84% and 83%, respectively, for the decisive class ‘wire bad’ classifying inadequate reinforcement.

23 April 2026 in IEEE Access
Verified
Journal Article
Open access
JSJannik Sobisch
Jannik Sobisch
JMJaden Myers
Jaden Myers
MFMirco Fuchs
Mirco Fuchs
ŽBŽiga Bizjak
Žiga Bizjak
Despite achieving high volumetric overlap, pixel-based deep learning segmentation approaches do not ensure true vascular connectivity, leading to fragmentations structurally analogous to Branch Retinal Artery Occlusions. This fundamental deficiency means that even segmentations achieving high pixel-wise overlap metrics (such as the Dice Score) do not guarantee or improve true vascular connectivity, rendering them unreliable for quantitative analysis and subsequent clinical risk stratification of high-risk systemic events, such as stroke. To resolve this, we introduce the Differentiable Endpoint Connectivity Loss (DECL), a novel, fully differentiable loss function that directly optimizes vascular continuity by precisely targeting errors in vessel endpoints. DECL leverages a differentiable soft-skeletonization module to impose two specialized penalties: a Normalized Count Penalty (Lc), which rigorously penalizes the discrete difference in the number of predicted versus true endpoints (ΔNp), and a Normalized Distance Loss (Ld), which penalizes the Euclidean distance between the weighted centers of the true and predicted endpoints. In comparative experiments across four datasets (DRIVE, CHASE DB1, STARE, and OCTA-500), we tested DECL against established methods including Dice CE, clDice, cbDice, and SAC Loss. DECL and its hybrid variant, DECLclDice, consistently recorded the highest mean Dice Score and clDice scores, specifically, DECLclDiced improved the mean clDice score from 0.839 to 0.851 on CHASE DB1 and from 0.836 to 0.842 on DRIVE, while minimizing Betti Number Error (β-Error) andVariation of Information. The DECL method establishes a robust, mathematically justified framework for generating high-fidelity vascular maps, essential for accurate biomarker quantification and reliable clinical assessment.